LiLAW: Lightweight Learnable Adaptive Weighting to Meta-Learn Sample Difficulty and Improve Noisy Training

Abhishek Moturu, Anna Goldenberg, Babak Taati

Keywords: reweighting, noise, mislabels, lightweight, adaptive, meta-learning, difficulty

TL;DR: lightweight method that adaptively reweights samples by difficulty to boost robustness under noise

Abstract: Training deep neural networks in the presence of noisy labels and data heterogeneity is a major challenge. We introduce Lightweight Learnable Adaptive Weighting (LiLAW), a novel method that dynamically adjusts the loss weight of each training sample based on its evolving difficulty level, categorized as easy, moderate, or hard. Using only three learnable parameters, LiLAW adaptively prioritizes informative samples throughout training by updating these weights using a single mini-batch gradient descent step on the validation set after each training mini-batch, without requiring excessive hyperparameter tuning or a clean validation set. Extensive experiments across multiple general and medical imaging datasets, noise levels and types, loss functions, and architectures with and without pretraining demonstrate that LiLAW consistently enhances performance, even in high-noise environments. It is effective without heavy reliance on data augmentation or advanced regularization, highlighting its practicality. It offers a computationally efficient solution to boost model generalization and robustness in any neural network training setup. Code in Supplementary Material.

Primary Area: transfer learning, meta learning, and lifelong learning

Submission Number: 5428